aws-cost-guard
claudeFind out why your AWS bill grew: costs by service, idle EC2, EBS and Elastic IPs, plus failing Kubernetes pods explained from logs. Read-only, uses your aws and kubectl CLI.
1 skill · 3 commands
Make Claude answer short and to the point: answer or code first, no filler, no repeated questions. A concise mode that saves reading time and output tokens.
Plugin caveman from marketplace petrovici-plugins in petrovicistefan/claude-code-plugins. Commands read from the repo's manifest — 1 month ago.
cavemanUse when the user wants short, direct answers without filler, for quick questions or when they only need the code.
/caveman:cavemanSwitch to short, direct answers until you ask for normal answers
Find out why your AWS bill grew: costs by service, idle EC2, EBS and Elastic IPs, plus failing Kubernetes pods explained from logs. Read-only, uses your aws and kubectl CLI.
1 skill · 3 commands
Find WCAG 2.2 accessibility problems in HTML, React, Vue, Svelte and Astro: missing alt text and labels, keyboard traps, focus issues and color contrast, then fix them.
1 skill · 2 commands
Write OpenAPI 3.1 docs from the real routes in Express, NestJS, Next.js, FastAPI, Flask, Spring and Go code, and check in CI that the docs still match the code.
1 skill · 2 commands
Load test your own API with a safe built-in runner or a generated k6 script: ramp-up, p50/p95/p99 latency, error rates and where it starts to saturate.
1 skill · 2 commands
Speed up and secure GitHub Actions and GitLab CI: find missing caches, wasted runs, missing timeouts, unpinned actions and flaky tests, using your real run times.
1 skill · 2 commands
Measure cyclomatic complexity, long functions, large files and duplicated code in Python, JavaScript, TypeScript, Java, Go and more, and track tech debt over time.
1 skill · 2 commands
Ultra-compressed communication mode. Cuts token usage 20-50% (75% upper bound) by dropping filler, articles, pleasantries, and hedging while keeping full technical accuracy. Derived from Matt Pocock's MIT-licensed caveman with: (1) 3 stdlib Python tools (deterministic compressor, token-savings estimator with $/Mtok cost extrapolation, lint that detects banned vocab with code-block + exception-zone whitelisting), (2) 3 references citing 7-8 sources (compression principles, when caveman backfires, companion tooling), (3) cs-caveman-mode persona agent + /cs-caveman slash command. Matt's persistence rules + auto-clarity exception preserved verbatim per MIT.
1 skill · 1 command · 1 agent
Create or update a pull request with a concise visual outline for reviewers
1 skill
Twelve-skill bundle covering the International Economic Review manuscript lifecycle.
12 skills
Writing guidance based on William Strunk Jr.'s The Elements of Style (1918) - foundational rules for clear, concise, grammatically correct writing
1 skill
MCP server that processes large outputs in sandboxed subprocesses and returns concise summaries instead of dumping raw data into the context window. Reduces token usage by up to 98%.
1 agent
Skill for legal research on Italian and EU sources: legislation, administrative practice, and case law. Encode a working method, not an opinion: routing to official sources, citations with verifiable references, validity checks including ratione temporis, query minimization for contexts covered by professional secrecy, and concise output by default. The Agent Skills format is an open standard: the skill was created for Claude (claude.ai, Desktop, Cowork, Claude Code) and is reusable in tools that adopt the same format.
200 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.